arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.11279cs.LGq-bio.QM
收藏

Tyger:用于分子性质预测的任务型通用主动学习

Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction

National University of Singapore(新加坡国立大学);ByteDance(字节跳动);HEC Montreal(蒙特利尔高等商学院);MILA(蒙特利尔学习算法研究所);Tencent(腾讯)

Kuangqi Zhou, Kaixin Wang, Jiashi Feng, Jian Tang, Tingyang Xu, Xinchao Wang

摘要:

如何准确预测分子的性质是AI驱动的药物发现中的一个本质问题,这通常需要大量的注释来训练深度学习模型。然而,注释分子是相当昂贵的,因为它需要由专家进行实验室实验。为了降低标注成本,开发了深度主动学习(AL)方法,以仅选择最具代表性和信息量最大的数据进行标注。然而,现有的最佳深度AL方法大多是针对单一类型的学习任务(例如,单标记分类),因此在涉及各种任务类型的分子性质预测中可能表现不佳。在本文中,我们提出了一个任务类型通用的主动学习框架(称为老虎),能够处理不同类型的学习任务,在一个统一的方式。关键是学习一个化学意义的嵌入空间,并完全基于嵌入执行主动选择,而不是依赖于特定于任务类型的算法(例如,分类预测概率),如现有工作中所做的那样。具体来说,为了学习嵌入空间,我们实例化了一个查询模块,该模块学习将分子图转换为相应的SMILES字符串。此外,为了确保从空间中选择的样本具有代表性和信息性,我们建议通过两个学习目标来塑造嵌入空间,一个基于领域知识,另一个利用来自任务学习者的反馈(即,执行手头的学习任务的模型)。我们在不同任务类型的基准数据集上进行了广泛的实验。实验结果表明,Tyger在分子性质预测上始终实现高AL性能,大幅优于基线。我们还进行烧蚀实验,以验证每个组件在泰格的有效性。

英文摘要:

How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery, which generally requires a large amount of annotation for training deep learning models. Annotating molecules, however, is quite costly because it requires lab experiments conducted by experts. To reduce annotation cost, deep Active Learning (AL) methods are developed to select only the most representative and informative data for annotating. However, existing best deep AL methods are mostly developed for a single type of learning task (e.g., single-label classification), and hence may not perform well in molecular property prediction that involves various task types. In this paper, we propose a Task-type-generic active learning framework (termed Tyger) that is able to handle different types of learning tasks in a unified manner. The key is to learn a chemically-meaningful embedding space and perform active selection fully based on the embeddings, instead of relying on task-type-specific heuristics (e.g., class-wise prediction probability) as done in existing works. Specifically, for learning the embedding space, we instantiate a querying module that learns to translate molecule graphs into corresponding SMILES strings. Furthermore, to ensure that samples selected from the space are both representative and informative, we propose to shape the embedding space by two learning objectives, one based on domain knowledge and the other leveraging feedback from the task learner (i.e., model that performs the learning task at hand). We conduct extensive experiments on benchmark datasets of different task types. Experimental results show that Tyger consistently achieves high AL performance on molecular property prediction, outperforming baselines by a large margin. We also perform ablative experiments to verify the effectiveness of each component in Tyger.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑